| name | live-transcribe |
| description | Start real-time microphone transcription using ElevenLabs Scribe v2 Realtime. Use when user wants to start live transcription, dictation, or real-time speech capture. Triggers on: 'ืชืชืืื ืชืืืื', 'ืชืืื ืืืื ืืืช', 'start transcribing', 'live transcribe', 'ืืงืื ืื ืฉืื ื ืืืืจ'. After starting, tell user they can say 'ืืืงื ืื ืืกืคืืง ืืื ื ืขืฆืืจ ืืช ืืชืืืื' to stop, or use /live-transcribe-stop. |
Live Transcribe โ Start
Start real-time microphone transcription. The script captures audio, streams to ElevenLabs Scribe v2 Realtime via WebSocket, and writes committed text to a temp file continuously.
Start command
source ~/.claude/skills/transcribe/scripts/.env && \
ELEVENLABS_API_KEY="$ELEVENLABS_API_KEY" \
nohup python3 ~/.claude/scripts/realtime-transcribe.py > /tmp/realtime-transcribe.log 2>&1 &
Wait ~4 seconds, then read the first line of /tmp/realtime-transcribe.log for the startup JSON:
{"status": "started", "pid": 12345, "output_file": "/tmp/transcribe-20260526-143022.txt", ...}
Before starting
Check if one is already running:
test -f /tmp/realtime-transcribe.pid && kill -0 $(cat /tmp/realtime-transcribe.pid) 2>/dev/null && echo "ALREADY RUNNING"
If already running, tell the user and offer to stop first.
What to tell the user
- Transcription is running
- The output file path
- Ways to stop: say "ืืืงื, ืื ืืกืคืืง, ืืื ื ืขืฆืืจ ืืช ืืชืืืื", or ask the agent to stop, or
/live-transcribe-stop
- They can ask to read the transcript anytime
Audio cues
Pre-recorded sounds play automatically:
- Start: "ืืชืืืชื ืชืืืื!" (before recording begins)
- Stop: "ืกืืืืชื ืืช ืืชืืืื." (after recording ends)
- Reminder: "ืื ื ืขืืืื ืืชืืื." (every 30 minutes)
